2018_Diatomite_aliphaticSRM

Start up functions

Read and organize data

read_srm_export <- function(filename, columns = c("peak_name", "RT.min", "basepeak", "area.cpm", "height.cts", "quantitation")) {
  filename %>% 
    # read excel files
    read_excel(sheet = "Integration", skip = 42, 
               col_names = columns, col_types = rep("text", length(columns))) %>% 
    as_data_frame() %>%
    # remove empty rows
    filter(!is.na(peak_name), peak_name != "n.a.") %>% 
    # convert the relevant numeric columns into numbers
    mutate_at(vars(RT.min, area.cpm, height.cts), as.numeric) %>% 
    # remove useless columns
    select(-basepeak, -quantitation) %>% 
    # add filename info
    mutate(file_id = gsub("\\.xls", "", basename(filename))) %>% 
    select(file_id, everything())
}

# get data
all_data <- 
  # find all excel files ##change name and use new folder for new project
  list.files("Diatomite", recursive = TRUE, full.names = TRUE, pattern = "\\.xls$") %>% 
  # send them to the read method
  lapply(read_srm_export) %>% 
  # combine the data set
  bind_rows() %>% 
  # pull out sample information
  #mutate(sample_id = str_match(all_data$file_id, "TSQ\\d+_GB_(.*)$") %>% { .[,2] }) %>% 
  # get n replicates
  group_by(file_id)
  #mutate(n_replicates = length(unique(file_id)))

Plot to check the spread

all_data %>% 
  ggplot() + 
  aes(x = peak_name, y = area.cpm, color = file_id) +
  geom_point(size = 3) +
  theme_bw() +
  theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1))

Calculation of peak amounts and rock concentrations, ID standards

depth_and_rock_info <- read_excel(file.path("metadata", "Diatomite paper OG sample data 05152018.xlsx")) %>% 
  rename(tle = `TLE.mg`, maltene = `maltenes.mg`, ref_amount_added.ug = `std_injected.ng`, injec_std_added.ug = `Retene.ng/ul`)%>% 
  filter(!is.na(file_id))
kable(depth_and_rock_info)

file_id	depth	rock.g	process	tle	maltene	std_added.ng	ref_amount_added.ug	injec_std_added.ug
TSQ3757_AM_MSC_OG124-1	2709	4.003	yes	0.00241	0.00221	100	75.0	0.05
TSQ3_AM_MSC_OG125-1	3393	5.100	yes	0.01977	0.01665	100	75.0	0.05
TSQ3_AM_MSC_OG126-1	3474	3.430	yes	0.02050	0.01432	100	75.0	0.05
TSQ3762_AM_MSC_OG210-1	3675	6.209	yes	0.03000	0.02778	120	90.0	0.05
TSQ3779_AM_MSC_OG229-1	3420	5.241	yes	0.04718	0.03633	170	127.5	0.05
TSQ3780_AM_MSC_OG230-1	3456	4.564	yes	0.02635	0.01828	170	127.5	0.05
TSQ3783_AM_MSC_OG231-1	3402	5.910	yes	0.04357	0.02838	170	127.5	0.05
TSQ3787_AM_MSC_OG237-1	3756	6.131	yes	0.00287	NA	100	75.0	0.05

data_by_depth <- 
  all_data %>%
  left_join(depth_and_rock_info, by = "file_id") %>% 
  group_by(file_id) %>% 
  mutate(
    n_peaks = n(),
    n_standards = sum(peak_name == "D4 C29 ISTD"),
    ref_area.cpm = area.cpm[peak_name == "D4 C29 ISTD"],
    amount.ug = area.cpm/ref_area.cpm * ref_amount_added.ug,
   
    #Normalize by what you want
    conc_rock.ug_g = amount.ug / rock.g, 
    conc_tle.ug.g = amount.ug / tle,  
    conc_maltene.ug.g = amount.ug / maltene ,
    
    #Injection Standard
    n_injec_std = sum(peak_name == "Retene InjSt"),
    injec_std_area.cpm = area.cpm[peak_name == "Retene InjSt"],
    injec_std_added.ug = .005 
     
  )%>% ungroup() %>% 
  arrange(file_id, peak_name) 

data_by_depth

Calculate injection volume

Linear regressions of the calibration curves

inj.standard <- read_excel(file.path("metadata", "Retene_calibration.xlsx"))   ###read excel

###Retene calibration curve
inj.standard %>% 
  ggplot() +
  aes(x = Known.ng, y = Measured_area.counts, color = calibration) + 
  geom_smooth(method = "lm", alpha = 0.5) +
  geom_point() +
  theme_bw() +
  theme(legend.position = "none") 

inj.calibrations <- 
  inj.standard %>% 
  filter(!is.na(calibration)) %>% 
  nest(-calibration) %>% 
  mutate(
    fit = map(data, ~summary(lm(`Measured_area.counts`~ `Known.ng`, data = .x))),
    coefficients = map(fit, "coefficients"),
    intercept = map_dbl(coefficients, `[`, 1, 1),
    intercept_se = map_dbl(coefficients, `[`, 1, 2),
    slope = map_dbl(coefficients, `[`, 2, 1),
    slope_se = map_dbl(coefficients, `[`, 2, 2),
    r2 = map_dbl(fit, "r.squared")
  )

#View(inj.calibrations)
inj.calibrations %>% select(-data, -fit, -coefficients) %>% knitr::kable(d = 3)

calibration	intercept	intercept_se	slope	slope_se	r2
jan2018	-3682.638	2154.729	1037185	10045.08	1

Calculate injection amount

data_w_inject <-
  data_by_depth %>% 
  # temp
  mutate(calibration = "jan2018") %>% 
  left_join(inj.calibrations, by = "calibration") %>% 
  mutate(
    total_volume.uL = 100,
    total_inject.uL = 1.5,
    retene_amount_inject_expected.ng = ((injec_std_added.ug/total_volume.uL) * total_inject.uL)*1000,
    retene_amount_inject_measured.ng = (injec_std_area.cpm - intercept)/slope,
    retene_amount_measured.ug = total_volume.uL/total_inject.uL * retene_amount_inject_measured.ng * 1/1000,
    inject_percent = (retene_amount_inject_measured.ng/retene_amount_inject_expected.ng)*100
  )
  
#View(data_w_inject)
#calib_data_corr <- calib_data %>% mutate(conc_rock.ug_g = amount_yield_corr.ug / `rock `) #in microgram lipid per gram rock
#View(calib_data_corr)

data_w_inject %>% 
  ggplot() +
  aes(x = file_id, y = inject_percent) + 
  geom_smooth(method = "lm", alpha = 0.5) +
  geom_point() +
  theme_bw() +
  theme(legend.position = "none") 

Calculate Recovery

Linear regressions of the calibration curves

standard <- read_excel(file.path("metadata", "D4_calibration.xlsx"))   ###read excel

###calibration curve
standard %>% 
  ggplot() +
  aes(x = Known.ng, y = Measured_area.counts, color = calibration) + 
  geom_smooth(method = "lm", alpha = 0.5) +
  geom_point() +
  theme_bw() +
  theme(legend.position = "none") 

calibrations <- 
  standard %>% 
  filter(!is.na(calibration)) %>% 
  nest(-calibration) %>% 
  mutate(
    fit = map(data, ~summary(lm(`Measured_area.counts`~ `Known.ng`, data = .x))),
    coefficients = map(fit, "coefficients"),
    intercept = map_dbl(coefficients, `[`, 1, 1),
    intercept_se = map_dbl(coefficients, `[`, 1, 2),
    slope = map_dbl(coefficients, `[`, 2, 1),
    slope_se = map_dbl(coefficients, `[`, 2, 2),
    r2 = map_dbl(fit, "r.squared")
  )

calibrations %>% select(-data, -fit, -coefficients) %>% knitr::kable(d = 3)

calibration	intercept	intercept_se	slope	slope_se	r2
jan2018	705.862	1371.146	72929.67	3337.256	0.996

Determine yield

This is not useful for anything else.

calib_data <-
  data_by_depth %>% 
  # temp
  mutate(calibration = "jan2018") %>% 
  left_join(calibrations, by = "calibration") %>% 
  mutate(
    total_volume.uL = 100,
    total_inject.uL = 1.5,
    ref_amount_inject_expected.ng = (ref_amount_added.ug * 1000)/total_volume.uL * total_inject.uL ,
    ref_amount_inject_measured.ng = (ref_area.cpm - intercept)/slope,
    ref_amount_measured.ug = ((total_volume.uL* ref_amount_inject_measured.ng)/total_inject.uL) * 1/1000,
    yield = (ref_amount_inject_measured.ng/ref_amount_inject_expected.ng) * 100
  )
  
calib_data

check yields

calib_data %>% 
  select(file_id, peak_name, yield)  %>% 
  arrange(file_id)  %>% 
  unique() %>% 
  ggplot() + aes(file_id, y = yield) +
  geom_point(size = 3) +
  theme_bw() + theme(axis.text.x = element_text(angle = 90, hjust = 0, vjust = 0.5))

Combine compounds/make ratios

# functions to make it easy to sum up peaks

sum_peaks <- function(df, filter_condition, new_peak_name) {
  filter_condition <- sprintf("(%s)", str_c(filter_condition, collapse = "|"))
  filter(df, str_detect(peak_name, filter_condition)) %>% 
    summarize(
      file_id = file_id[1],
      depth = depth[1],
      conc_tle.ug.g = sum(conc_tle.ug.g)
    ) %>% 
    mutate(peak_name = new_peak_name)
}

ratio_peaks <- function(df, filter_top, filter_bottom, new_peak_name) {
  filter_top <- sprintf("(%s)", str_c(filter_top, collapse = "|"))
  filter_bottom <- sprintf("(%s)", str_c(filter_bottom, collapse = "|"))
  filter(df, str_detect(peak_name, filter_top) | str_detect(peak_name, filter_bottom)) %>% 
    summarize(
      file_id = file_id[1],
      depth = depth[1],
      ratio = sum(conc_tle.ug.g[str_detect(peak_name, filter_top)]) / sum(conc_tle.ug.g[str_detect(peak_name, filter_bottom)])
    ) %>% 
    mutate(peak_name = new_peak_name)
}

Ratios, sums

#set values to use for later calculations
final_data1 <- calib_data %>% 
    group_by(file_id) %>% 
        do({
          bind_rows(., 
              #C27_Dia/Reg
                sum_peaks(.,  c("C27 aB 20R ST", "C27 aB 20S ST"), "C27Dia"),      
                sum_peaks(., c("C27 aaa 20R ST", "C27 aaa 20S ST", "C27 aBB 20R ST", "C27 aBB 20S ST", "C27 Ba 20R ST", "C27 Ba 20S ST"), "C27Reg"),
            
              #Total Tricyclics
                sum_peaks(., c("C19 Tri HO", "C20 Tri HO", "C21 Tri HO", "C22 Tri HO", "C23 Tri HO", "C24 Tet HO", "C24 Tri HO", "C25 Tri R HO", "C25 Tri S HO", "C26 Tri R HO", "C26 Tri S HO"), "all_tricyclics"),
            
              #4Me_TriMe
                sum_peaks(., c("4B Me 5a cholestane", "4B Me 24 ethyl 5a cholestane", "4B,23S,24S trimethyl 5a cholestane", "4B,23S,24R trimethyl 5a cholestane", "4B,23R,24S trimethyl 5a cholestane", "4B,23R,24R trimethyl 5a cholestane", "4a Me 5a cholestane", "4a Me 24 ethyl 5a cholestane", "4a,23S,24S trimethyl 5a cholestane", "4a,23S,24R trimethyl 5a cholestane", "4a,23R,24S trimethyl 5a cholestane", "4a,23R,24R trimethyl 5a cholestane"), "4Me_TriMe"),
            
              #allRegSt
                sum_peaks(., c("C26 aBB 20S ST", "C26 aBB 20R ST", "C26 aaa 20S ST", "C26 aaa 20R ST","C27 aBB 20S ST", "C27 aBB 20R ST", "C27 aaa 20S ST", "C27 aaa 20R ST", "C28 aBB 20S ST", "C28 aBB 20R ST", "C28 aaa 20S ST", "C28 aaa 20R ST","C29 aBB 20S ST", "C29 aBB 20R ST", "C29 aaa 20S ST", "C29 aaa 20R ST", "C30 aBB 20 R+S ST", "C30 aaa 20S ST", "C30 aaa 20R ST"), "allRegst"),
            
              #allRegHO
                sum_peaks(., c("Ts C27 HO", "Tm C27 HO", "C27 17B H Ho", "29, 30 C28H bisnor HO", "28, 30 C28 bisnor HO", "C29 Ts HO", "C29 Ba HO", "C29 BB Ho", "C30 aB HO", "C30 BB HO", "C30H Ba HO", "C31 HR Ba HO", "C31 aB HR HO", "C31 aB HS HO", "C31 BB HO", "C32 aB HS HO", "C32 aB HR HO", "C33 aB HS HO", "C33 aB HR HO", "C34 aB HR HO", "C34 aB HS HO", "C35 aB HR HO", "C35 aB HS HO"), "allRegHO") 
            
) }) %>% ungroup()

final_data <- final_data1 %>% 
    group_by(file_id) %>% 
        do({
          bind_rows(., 
           #Source
              #C19/tricyclics
                ratio_peaks(., "C19 Tri HO", "all_tricyclics", "C19/tricyclics"),
              #C20/tricyclics
                ratio_peaks(., "C20 Tri HO", "all_tricyclics", "C20/tricyclics"),
              #C21/tricyclics
                ratio_peaks(., "C21 Tri HO", "all_tricyclics", "C21/tricyclics"),
              #C22/tricyclics
                ratio_peaks(., "C22 Tri HO", "all_tricyclics", "C22/tricyclics"),
              #C23/tricyclics
                ratio_peaks(., "C23 Tri HO", "all_tricyclics", "C23/tricyclics"),
              #C24/tricyclics
                ratio_peaks(., c("C24 Tet HO", "C24 Tri HO"), "all_tricyclics", "C24/tricyclics"),
              #C25/tricyclics
                ratio_peaks(., c("C25 Tri R HO", "C25 Tri S HO"), "all_tricyclics", "C25/tricyclics"),
              #C26/tricyclics
                ratio_peaks(., c("C26 Tri R HO", "C26 Tri S HO"), "all_tricyclics", "C26/tricyclics"),
              #tricyclics/all
                ratio_peaks(., "all_tricyclics", c(""), "tricyclics/all"),
              #C19/C19+23
                ratio_peaks(., "C19 Tri HO", c("C19 Tri HO", "C23 Tri HO"), "C19/C19+23"),
              #C20/C20+23
                ratio_peaks(., "C20 Tri HO", c("C20 Tri HO", "C23 Tri HO"), "C20/C20+23"),
           
              #C26St/allSt ##INCLUDES ME's
                ratio_peaks(., c("C26 Ba 20S ST", "C26 Ba 20R ST", "C26 aBB 20S ST", "C26 aBB 20R ST", "C26 aaa 20S ST", "C26 aaa 20R ST"), c("cholestane", "ST"), "C26St/allSt"), 
              #C27St/allSt
                ratio_peaks(., c("C27 aaa 20R ST", "C27 aaa 20S ST", "C27 aBB 20R ST", "C27 aBB 20S ST", "C27 Ba 20R ST", "C27 Ba 20S ST"), c("cholestane", "ST"), "C27St/allSt"),
              #C28St/allSt
                ratio_peaks(., c("C28 Ba 20S ST", "C28 Ba 20R ST", "C28 aBB 20S ST", "C28 aBB 20R ST", "C28 aaa 20S ST", "C28 aaa 20R ST"), c("cholestane", "ST"), "C28St/allSt"),
              #C29St/allSt
                ratio_peaks(., c("C29 Ba 20S ST", "C29 Ba 20R ST", "C29 aBB 20S ST", "C29 aBB 20R ST", "C29 aaa 20S ST", "C29 aaa 20R ST"), c("cholestane", "ST"), "C29St/allSt"),
              #C30St/allSt (does not include Me's in numerator)
                ratio_peaks(., c("C30 Ba 20S ST", "C30 Ba 20R ST", "C30 aBB 20(R+S) ST", "C30 aaa 20S ST", "C30 aaa 20R ST"), c("cholestane", "ST"), "C30St/allSt"),
              #C30Me/allSt (C30 Me's in numerator)(not in MRM spreadsheet)
                ratio_peaks(., c("C30 4a Me 20S ST", "C30 4a Me 20R ST + DINO st", "C30 3B Me BB 20S ST", "C30 3B Me BB 20R ST", "C30 3B Me 20S ST", "C30 3BMe 20R ST", "C30 2aMe 20S ST", "C30 2a Me 20R + 4a Me BB 20S ST"), c("cholestane", "ST"), "C30Me/allSt"),
              #DinoSt/allSt
                ratio_peaks(., c("4B Me 5a cholestane", "4B Me 24 ethyl 5a cholestane", "4B,23S,24S trimethyl 5a cholestane", "4B,23S,24R trimethyl 5a cholestane", "4B,23R,24S trimethyl 5a cholestane", "4B,23R,24R trimethyl 5a cholestane", "4a Me 5a cholestane", "4a Me 24 ethyl 5a cholestane", "4a,23S,24S trimethyl 5a cholestane", "4a,23S,24R trimethyl 5a cholestane", "4a,23R,24S trimethyl 5a cholestane", "4a,23R,24R trimethyl 5a cholestane"), c("cholestane", "ST"), "DinoSt/allSt"),
           
              #C26/(C26-30)aaaSR
                ratio_peaks(., c("C26 aaa 20R ST", "C26 aaa 20S ST"), c("aaa 20R ST", "aaa 20S ST") , "C26/(C26-30)aaaSR"),
              #C27/(C26-30)aaaSR
                ratio_peaks(., c("C27 aaa 20R ST", "C27 aaa 20S ST"), c("aaa 20R ST", "aaa 20S ST") , "C27/(C26-30)aaaSR"),
              #C28/(C26-30)aaaSR
                ratio_peaks(., c("C28 aaa 20R ST", "C28 aaa 20S ST"), c("aaa 20R ST", "aaa 20S ST") , "C28/(C26-30)aaaSR"),
              #C29/(C26-30)aaaSR
                ratio_peaks(., c("C29 aaa 20R ST", "C29 aaa 20S ST"), c("aaa 20R ST", "aaa 20S ST") , "C29/(C26-30)aaaSR"),
              #C30/(C26-30)aaaSR
                ratio_peaks(., c("C30 aaa 20R ST", "C30 aaa 20S ST"), c("aaa 20R ST", "aaa 20S ST") , "C30/(C26-30)aaaSR"),
           
              #C27/C27+C28aaa&abb
                ratio_peaks(., c("C27 aaa 20R ST" , "C27 aaa 20S ST", "C27 aBB 20R ST", "C27 aBB 20S ST"), c("C27 aaa 20R ST" , "C27 aaa 20S ST", "C27 aBB 20R ST", "C27 aBB 20S ST", "C28 aaa 20R ST", "C28 aaa 20S ST", "C28 aBB 20R ST", "C28 aBB 20S ST")  , "C27/C27+C28aaa&abb"),
              #C27/C27+C29aaa&abb
                ratio_peaks(., c("C27 aaa 20R ST" , "C27 aaa 20S ST", "C27 aBB 20R ST", "C27 aBB 20S ST"), c("C27 aaa 20R ST" , "C27 aaa 20S ST", "C27 aBB 20R ST", "C27 aBB 20S ST", "C29 aaa 20R ST", "C29 aaa 20S ST", "C29 aBB 20R ST", "C29 aBB 20S ST")  , "C27/C27+C29aaa&abb"),
              #C28/C28+C27aaa&abb
                ratio_peaks(., c("C28 aaa 20R ST", "C28 aaa 20S ST", "C28 aBB 20R ST", "C28 aBB 20S ST"), c("C27 aaa 20R ST" , "C27 aaa 20S ST", "C27 aBB 20R ST", "C27 aBB 20S ST", "C28 aaa 20R ST", "C28 aaa 20S ST", "C28 aBB 20R ST", "C28 aBB 20S ST")  , "C28/C28+C27aaa&abb"),
              #C28/C28+C29aaa&abb
                ratio_peaks(., c("C28 aaa 20R ST", "C28 aaa 20S ST", "C28 aBB 20R ST", "C28 aBB 20S ST"), c("C29 aaa 20R ST", "C29 aaa 20S ST", "C29 aBB 20R ST", "C29 aBB 20S ST", "C28 aaa 20R ST", "C28 aaa 20S ST", "C28 aBB 20R ST", "C28 aBB 20S ST")  , "C28/C28+C29aaa&abb"),
              #C29/C29+C27aaa&abb
                ratio_peaks(., c("C29 aaa 20R ST", "C29 aaa 20S ST", "C29 aBB 20R ST", "C29 aBB 20S ST"), c("C27 aaa 20R ST" , "C27 aaa 20S ST", "C27 aBB 20R ST", "C27 aBB 20S ST", "C29 aaa 20R ST", "C29 aaa 20S ST", "C29 aBB 20R ST", "C29 aBB 20S ST")  , "C29/C29+C27aaa&abb"),
              #C29/C29+C28aaa&abb
                ratio_peaks(., c("C29 aaa 20R ST", "C29 aaa 20S ST", "C29 aBB 20R ST", "C29 aBB 20S ST"), c("C29 aaa 20R ST", "C29 aaa 20S ST", "C29 aBB 20R ST", "C29 aBB 20S ST", "C28 aaa 20R ST", "C28 aaa 20S ST", "C28 aBB 20R ST", "C28 aBB 20S ST")  , "C29/C29+C28aaa&abb"),
              
              #4Me_TriMe/Me_C26St
                ratio_peaks(., c("4Me_TriMe"), c("4Me_TriMe", "C26 aBB 20S ST", "C26 aBB 20R ST", "C26 aaa 20S ST", "C26 aaa 20R ST") , "4Me_TriMe/Me_C26St"),
              #4Me_TriMe/Me_C27St
                ratio_peaks(., c("4Me_TriMe"), c("4Me_TriMe", "C27 aBB 20S ST", "C27 aBB 20R ST", "C27 aaa 20S ST", "C27 aaa 20R ST") , "4Me_TriMe/Me_C27St"),
              #4Me_TriMe/Me_C28St
                ratio_peaks(., c("4Me_TriMe"), c("4Me_TriMe", "C28 aBB 20S ST", "C28 aBB 20R ST", "C28 aaa 20S ST", "C28 aaa 20R ST") , "4Me_TriMe/Me_C28St"),
              #4Me_TriMe/Me_C29St
                ratio_peaks(., c("4Me_TriMe"), c("4Me_TriMe", "C29 aBB 20S ST", "C29 aBB 20R ST", "C29 aaa 20S ST", "C29 aaa 20R ST") , "4Me_TriMe/Me_C29St"),
              #4Me_TriMe/Me_C30St
                ratio_peaks(., c("4Me_TriMe"), c("4Me_TriMe", "C30 aBB 20 R+S ST", "C30 aaa 20S ST", "C30 aaa 20R ST") , "4Me_TriMe/Me_C30St"),
              #4Me_TriMe/Me_allSt
                ratio_peaks(., c("4Me_TriMe"), c("4Me_TriMe", "allRegst") , "4Me_TriMe/Me_allSt"),
           
              #C26-30St/C26-C30St+regHo 
                ratio_peaks(., c("allRegst"), c("allRegst", "Ts C27 HO", "Tm C27 HO", "C27 17B HO", "29, 30 C28 bisnor HO", "28, 30 C28 bisnor HO", "C29 Ts HO", "C29 Ba HO", "C29 BB Ho", "C30 aB HO", "C30 BB HO", "C30H Ba HO", "C31 HR Ba HO", "C31 aB HR HO", "C31 aB HS HO", "C31 BB HO", "C32 aB HS HO", "C32 aB HR HO", "C33 aB HS HO", "C33 aB HR HO", "C34 aB HR HO", "C34 aB HS HO", "C35 aB HR HO", "C35 aB HS HO"), "C26-30St/C26-C30St_regHo"),
              #C27-C30aaaSt/C27-C30aaaSt+regHo
                ratio_peaks(., c( "C26 aaa 20S ST", "C26 aaa 20R ST", "C27 aaa 20S ST", "C27 aaa 20R ST", "C28 aaa 20S ST", "C28 aaa 20R ST", "C29 aaa 20S ST", "C29 aaa 20R ST", "C30 aaa 20S ST", "C30 aaa 20R ST"), c("C26 aaa 20S ST", "C26 aaa 20R ST", "C27 aaa 20S ST", "C27 aaa 20R ST", "C28 aaa 20S ST", "C28 aaa 20R ST", "C29 aaa 20S ST", "C29 aaa 20R ST", "C30 aaa 20S ST", "C30 aaa 20R ST", "allRegHO"), "C27-C30aaaSt/C27-C30aaaSt+regHo"),
              #Ho/St
                ratio_peaks(., "allRegHO", c("C26 aaa 20S ST", "C26 aaa 20R ST", "C27 aaa 20S ST", "C27 aaa 20R ST", "C28 aaa 20S ST", "C28 aaa 20R ST", "C29 aaa 20S ST", "C29 aaa 20R ST", "C30 aaa 20S ST", "C30 aaa 20R ST"), "Ho/St"),
              #Ho/St%
                ratio_peaks(., "allRegHO", c("C26 aaa 20S ST", "C26 aaa 20R ST", "C27 aaa 20S ST", "C27 aaa 20R ST", "C28 aaa 20S ST", "C28 aaa 20R ST", "C29 aaa 20S ST", "C29 aaa 20R ST", "C30 aaa 20S ST", "C30 aaa 20R ST", "allRegHO" ), "Ho/St%"),
            
              #C31_2MHI
                ratio_peaks(., "C31 2a Me Ho", c("C30 aB HO", "C31 2a Me Ho" ), "C31_2MHI"),
              #C31_35_2MHI
                ratio_peaks(., c("C31 2a Me Ho", "C32 2aMe R HO", "C32 2aMe S HO", "C33 2aMe S HO", "C33 2aMe R HO", "C34 2a Me S HO", "C34 2a Me R HO", "C36 2a Me R HO", "C36 2a Me S HO"), c("C30 aB HO", "C31 2a Me Ho", "C32 2aMe R HO", "C32 2aMe S HO", "C33 2aMe S HO", "C33 2aMe R HO", "C34 2a Me S HO", "C34 2a Me R HO", "C36 2a Me R HO", "C36 2a Me S HO"), "C31_35_2MHI"),
              #C31_2-MHI/C27-C30Steranes
                ratio_peaks(., "C31 2a Me Ho", c("C26 aaa 20S ST", "C26 aaa 20R ST", "C27 aaa 20S ST", "C27 aaa 20R ST" ,"C28 aaa 20S ST", "C28 aaa 20R ST", "C29 aaa 20S ST", "C29 aaa 20R ST", "C30 aaa 20S ST", "C30 aaa 20R ST", "C31 2a Me Ho" ), "C31_2-MHI/C27-C30Steranes"),
              #C31 3-MHI 
                ratio_peaks(., "C31 3B Me HO", c("C31 3B Me HO", "C30 aB HO"), "C31 3-MHI"), 
              #C31_35_3MHI(%)
                 ratio_peaks(., c("C31 3B Me HO", "C32 3B Me S HO", "C32 3B Me R HO", "C32 3B Me Ba 22S+R ST", "C33 3BMe S HO", "   
C33 3BMe R HO", "C34 3B Me S Ho", "C34 3B Me R HO", "C35 3B Me R HO", "C35 3B Me S HO", "C36 3B Me S HO", "C36 3B Me R HO"), c("C30 aB HO","C31 3B Me HO", "C32 3B Me S HO", "C32 3B Me R HO", "C32 3B Me Ba 22S+R ST", "C33 3BMe S HO", "C33 3BMe R HO", "C34 3B Me S HO", "C34 3B Me R HO", "C35 3B Me R HO", "C35 3B Me S HO", "C36 3B Me S HO", "C36 3B Me R HO" ) ,"C31_35_3MHI(%)"),

              #C29ab/C29ab+C30ab
                 ratio_peaks(., "C29 aB HO", c( "C29 aB HO" , "C30 aB HO"), "C29ab/C29ab+C30ab"), 
              #C29ab/allHoab
                 ratio_peaks(., "C29 aB HO" , c("C35 aB HS HO", "C35 aB HR HO", "C34 aB HS HO", "C34 aB HR HO", "C33 aB HS HO" , "C33 aB HR HO", "C32 aB HR HO", "C32 aB HS HO", "C31 aB HS HO", "C31 aB HR HO", "C30 aB HO", "C29 aB HO"), "C29ab/allHoab"), 
              #C30ab/allHoab 
                 ratio_peaks(., "C30 aB HO" , c("C35 aB HS HO", "C35 aB HR HO", "C34 aB HS HO", "C34 aB HR HO", "C33 aB HS HO" , "C33 aB HR HO", "C32 aB HR HO", "C32 aB HS HO", "C31 aB HS HO", "C31 aB HR HO", "C30 aB HO", "C29 aB HO"), "C30ab/allHoab"), 
              #C31ab/allHoab 
                 ratio_peaks(., c("C31 aB HS HO", "C31 aB HR HO") , c("C35 aB HS HO", "C35 aB HR HO", "C34 aB HS HO", "C34 aB HR HO", "C33 aB HS HO" , "C33 aB HR HO", "C32 aB HR HO", "C32 aB HS HO", "C31 aB HS HO", "C31 aB HR HO", "C30 aB HO", "C29 aB HO"), "C31ab/allHoab"),
              #C32ab/allHoab 
                 ratio_peaks(., c("C32 aB HR HO", "C32 aB HS HO") , c("C35 aB HS HO", "C35 aB HR HO", "C34 aB HS HO", "C34 aB HR HO", "C33 aB HS HO" , "C33 aB HR HO", "C32 aB HR HO", "C32 aB HS HO", "C31 aB HS HO", "C31 aB HR HO", "C30 aB HO", "C29 aB HO"), "C32ab/allHoab"),
              #C33ab/allHoab 
                 ratio_peaks(., c( "C33 aB HS HO" , "C33 aB HR HO") , c("C35 aB HS HO", "C35 aB HR HO", "C34 aB HS HO", "C34 aB HR HO", "C33 aB HS HO" , "C33 aB HR HO", "C32 aB HR HO", "C32 aB HS HO", "C31 aB HS HO", "C31 aB HR HO", "C30 aB HO", "C29 aB HO"), "C33ab/allHoab"),
              #C34ab/allHoab 
                 ratio_peaks(., c( "C34 aB HS HO", "C34 aB HR HO") , c("C35 aB HS HO", "C35 aB HR HO", "C34 aB HS HO", "C34 aB HR HO", "C33 aB HS HO" , "C33 aB HR HO", "C32 aB HR HO", "C32 aB HS HO", "C31 aB HS HO", "C31 aB HR HO", "C30 aB HO", "C29 aB HO"), "C34ab/allHoab"),
              #C35ab/allHoab 
                 ratio_peaks(., c("C35 aB HS HO", "C35 aB HR HO") , c("C35 aB HS HO", "C35 aB HR HO", "C34 aB HS HO", "C34 aB HR HO", "C33 aB HS HO" , "C33 aB HR HO", "C32 aB HR HO", "C32 aB HS HO", "C31 aB HS HO", "C31 aB HR HO", "C30 aB HO", "C29 aB HO"), "C35ab/allHoab"),
              #OleananeIndex
                ratio_peaks(., "Oleanane HO", c("Oleanane HO", "C30 aB HO"), "OleananeIndex"),

            #Source
              #HHI
                ratio_peaks(., c("C35 aB HS HO", "C35 aB HR HO") , c("C35 aB HS HO", "C35 aB HR HO", "C34 aB HS HO", "C34 aB HR HO", "C33 aB HS HO" , "C33 aB HR HO", "C32 aB HR HO", "C32 aB HS HO", "C31 aB HS HO", "C31 aB HR HO"), "HHI"),
              #C35/C35+C34
                ratio_peaks(., c("C35 aB HS HO", "C35 aB HR HO"), c("C34 aB HS HO", "C34 aB HR HO","C35 aB HS HO", "C35 aB HR HO"), "C35/C35+C34"),
              #GI
                ratio_peaks(., "gamma", c("gamma", "C30 aB HO"), "GI"),
              #28,30BNH/28,30BNH+C30
                ratio_peaks(., "28, 30 C28 bisnor HO", c("28, 30 C28 bisnor HO", "C30 aB HO"), "28,30BNH/28,30BNH+C30") ,

 #Thermal Maturity
              #C27_Dia/Reg
                ratio_peaks(., "C27Dia", "C27Reg", "C27Dia/Reg"),
              #C27Dia_S/R
                ratio_peaks(., "C27 aB 20S ST", "C27 aB 20R ST", "C27Dia_S/R"),
              #C27Dia_S/S+R
                ratio_peaks(., "C27 aB 20S ST", c("C27 aB 20S ST", "C27 aB 20R ST"), "C27Dia_S/S+R") ,
              #C27Reg_abb/all 
                 ratio_peaks(., c("C27 aBB 20R ST", "C27 aBB 20S ST"), c("C27 aaa 20R ST", "C27 aaa 20S ST", "C27 aBB 20R ST", "C27 aBB 20S ST"), "C27Reg_abb/aaa"),
              #C27RegaaaS/S+R
                ratio_peaks(., "C27 aaa 20S ST", c("C27 aaa 20R ST", "C27 aaa 20S ST"), "C27Regaaa_S/S+R"), 
              #C27RegabbS/S+R
                ratio_peaks(., "C27 aBB 20S ST", c("C27 aBB 20S ST", "C27 aBB 20R ST"), "C27Regabb_S/S+R"),
              #C28Dia/all
                ratio_peaks(., c("C28 Ba 20S ST", "C28 Ba 20R ST"), c("C28 aBB 20S ST", "C28 aBB 20R ST", "C28 aaa 20S ST", "C28 aaa 20R ST", "C28 Ba 20S ST", "C28 Ba 20R ST"), "C28Dia/all"),
              #C28DiaS/S+R
                ratio_peaks(., "C28 Ba 20S ST", c("C28 Ba 20S ST", "C28 Ba 20R ST"), "C28DiaS/S+R"),
              #C28abb/all
                ratio_peaks(., c("C28 aBB 20S ST", "C28 aBB 20R ST"), c("C28 aBB 20S ST", "C28 aBB 20R ST", "C28 aaa 20S ST", "C28 aaa 20R ST"), "C28abb/all"),
              #C28aaaS/S+R
                ratio_peaks(., "C28 aaa 20S ST", c("C28 aaa 20S ST", "C28 aaa 20R ST"), "C28aaaS/S+R"),
              #C28abbS/S+R
                ratio_peaks(., "C28 aBB 20S ST", c("C28 aBB 20S ST", "C28 aBB 20R ST"), "C28abbS/S+R"),
              #C29Dia/all
                ratio_peaks(., c("C29 Ba 20S ST", "C29 Ba 20R ST"),  c("C29 Ba 20S ST", "C29 Ba 20R ST", "C29 aBB 20S ST", "C29 aBB 20R ST", "C29 aaa 20S ST", "C29 aaa 20R ST"), "C29Dia/all"),
              #C29DiaS/S+R
                ratio_peaks(., "C29 Ba 20S ST", c("C29 Ba 20S ST", "C29 Ba 20R ST"), "C29DiaS/S+R"),
              #C29abb/all
                ratio_peaks(., c("C29 aBB 20S ST", "C29 aBB 20R ST"), c( "C29 aaa 20S ST", "C29 aaa 20R ST", "C29 aBB 20S ST", "C29 aBB 20R ST" ), "C29abb/all"),
              #C29aaaS/S+R
                ratio_peaks(., "C29 aaa 20S ST", c("C29 aaa 20S ST", "C29 aaa 20R ST") , "C29aaaS/S+R"),
              #C29abbS/S+R
                ratio_peaks(., "C29 aBB 20S ST", c("C29 aBB 20S ST", "C29 aBB 20R ST"), "C29abbS/S+R"),
              #C27Ts/Ts+Tm
                ratio_peaks(., "Ts C27 HO", c("Ts C27 HO", "Tm C27  HO"), "C27Ts/Tm"),
              #C28BNH29,30/28,30
                ratio_peaks(., "29, 30 C28 bisnor HO", c("29, 30 C28 bisnor HO", "28, 30 C28 bisnor HO"), "C28BNH29,30/28,30"),
              #C29Ts/Ts+ab
                ratio_peaks(., "C29 Ts HO", c( "C29 aB HO", "C29 Ts HO"), "C29Ts/ab"),
              #C29ba/ba+ab
                ratio_peaks(.,"C29 Ba HO",  c("C29 aB HO", "C29 Ba HO"), "C29ba/ab"),
              #C29bb/bb+ab
                ratio_peaks(., "C29 BB Ho", c("C29 BB Ho", "C29 aB HO"), "C29bb/ab"),
              #C30_30nor/30nor+ab
                ratio_peaks(., "30-nor C30H HO", c("C30 aB HO", "30-nor C30H HO"),  "C30_30nor/ab"),
              #C30ba/ba+ab
                ratio_peaks(., "C30H Ba HO", c("C30 aB HO", "C30H Ba HO"), "C30ba/ab"),
              #C30bb/bb+ab
                ratio_peaks(., "C30 BB HO", c("C30 aB HO", "C30 BB HO"), "C30bb/ab"),
              #C31S/S+R
                ratio_peaks(., "C31 aB HS  HO", c("C31 aB HR HO", "C31 aB HS  HO"), "C31S/S+R"),
              #C32S/S+R
                ratio_peaks(., "C32 aB HS HO", c("C32 aB HS HO", "C32 aB HR HO"), "C32S/S+R"),
              #C33S/S+R
                ratio_peaks(., "C33 aB HS HO", c("C33 aB HS HO", "C33 aB HR HO"), "C33S/S+R"),
              #C34S/S+R
                ratio_peaks(., "C34 aB HS HO", c("C34 aB HS HO", "C34 aB HR HO") , "C34S/S+R"),
              #C35S/S+R
                ratio_peaks(., "C35 aB HS HO", c("C35 aB HS HO", "C35 aB HR HO") , "C35S/S+R")
              
 ) }) %>% ungroup() 
  
final_data

Plots

Thermal Maturity

C27Dia/Reg

subset(final_data, peak_name == "C27Dia/Reg") %>%
  ggplot() +
  aes(x = depth, y = ratio) +
  geom_point() +
  geom_line() +
  facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

DiaS/S+R

subset(final_data, peak_name%in% c("C27Dia_S/S+R", "C28DiaS/S+R" , "C29DiaS/S+R")) %>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  geom_line() +
  #facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

C27Regabb/aaa

subset(final_data, peak_name== "C27Reg_abb/aaa") %>%
  ggplot() +
  aes(x = depth, y = ratio) +
  geom_line() +
  geom_point() +
  facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

aaa_S/S+R

final_data %>%
  filter(peak_name %in% c("C27Regaaa_S/S+R", "C28aaaS/S+R", "C29aaaS/S+R")) %>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_line() +
  geom_point() +
  facet_grid(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

abb_s/s+r

subset(final_data, peak_name %in% c("C27Regabb_S/S+R", "C28abbS/S+R", "C29abbS/S+R")) %>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  #facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

C28/9Dia/all

subset(final_data, peak_name %in% c("C28Dia/all", "C29Dia/all")) %>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  geom_line() +
  #facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

C28/9abb/all

subset(final_data, peak_name %in% c("C28abb/all", "C29abb/all"))  %>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  geom_line() +
  #facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip() 

C27Ts/Tm

subset(final_data, peak_name== "C27Ts/Tm") %>%
  ggplot() +
  aes(x = depth, y = ratio) +
  geom_point() +
  geom_line() +
  facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

C28BNH29,30/28,30

subset(final_data, peak_name == "C28BNH29,30/28,30") %>%
  ggplot() +
  aes(x = depth, y = ratio) +
  geom_point() +
  geom_line() +
  facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

C29Ts/ab

subset(final_data, peak_name== "C29Ts/ab") %>%
  ggplot() +
  aes(x = depth, y = ratio) +
  geom_point() +
  geom_line() +
  facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

C29,30ba/ab

subset(final_data, peak_name %in% c("C29ba/ab", "C30ba/ab")) %>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  geom_line() +
  #facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

C29bb/ab

subset(final_data, peak_name %in% c("C29bb/ab", "C30bb/ab")) %>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  geom_line() +
  #facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

C30_30nor/ab

subset(final_data, peak_name== "C30_30nor/ab") %>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  geom_line() +
  #facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

subset(final_data, peak_name %in% c("C30 aB HO", "C30H Ba HO")) %>%
  ggplot() +
  aes(x = depth, y = conc_tle.ug.g, color = peak_name) +
  geom_point() +
  #facet_wrap(~peak_name) +
  scale_x_reverse() +
  geom_line() +
  coord_flip()

Steranes - Source

Sterane over All Steranes

subset(final_data, peak_name %in% c("DinoSt/allSt", "C30Me/allSt", "C30St/allSt", "C29St/allSt", "C28St/allSt", "C27St/allSt", "C26St/allSt")) %>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  geom_line() +
  coord_flip() +
  facet_grid(~peak_name, scales = "free") +
  scale_x_reverse()

Sterane over All aaa Steranes

subset(final_data, peak_name %in% c("C30/(C26-30)aaaSR", "C29/(C26-30)aaaSR", "C28/(C26-30)aaaSR", "C27/(C26-30)aaaSR",  "C26/(C26-30)aaaSR")) %>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  geom_line() +
  coord_flip() +
  facet_grid(~peak_name, scales = "free") +
  scale_x_reverse()

Sterane over aaa&abb Steranes

subset(final_data, peak_name %in% c ("C29/C29+C28aaa&abb", "C29/C29+C27aaa&abb", "C28/C28+C29aaa&abb", "C28/C28+C27aaa&abb", "C27/C27+C29aaa&abb",  "C27/C27+C28aaa&abb")) %>%
  ggplot() +
  aes(x = depth, y = ratio,color = peak_name) +
  geom_point() +
  geom_line() +
  coord_flip() +
  facet_grid(~peak_name, scales = "free") +
  scale_x_reverse()

4Me’s

subset(final_data, peak_name %in% c("4Me_TriMe/Me_allSt", "4Me_TriMe/Me_C30St", "4Me_TriMe/Me_C29St", "4Me_TriMe/Me_C28St", "4Me_TriMe/Me_C27St",  "4Me_TriMe/Me_C26St")) %>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  coord_flip() +
  geom_line() +
  facet_grid(~peak_name, scales = "free") +
  scale_x_reverse()

Steranes and Hopanes

subset(final_data, peak_name== "C26-30St/C26-C30St_regHo") %>%
  ggplot() +
  aes(x = depth, y = ratio) +
  geom_point() +
  geom_line() +
  coord_flip() +
  facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse()

subset(final_data, peak_name== "C27-C30aaaSt/C27-C30aaaSt+regHo") %>%
  ggplot() +
  aes(x = depth, y = ratio) +
  geom_point() +
  geom_line() +
  coord_flip() +
  facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse()

subset(final_data, peak_name== "Ho/St") %>%
  ggplot() +
  aes(x = depth, y = ratio) +
  geom_point() +
  geom_line() +
  coord_flip() +
  facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse()

Hopanes - Source

tricyclics

subset(final_data, peak_name %in% c("C19/tricyclics" , "C20/tricyclics" , "C21/tricyclics" , "C22/tricyclics" , "C23/tricyclics" , "C24/tricyclics" , "C25/tricyclics" , "C26/tricyclics")) %>%
  ggplot() +
  #geom_area(mapping = aes(fill = peak_name)) +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  geom_line() +
  #facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

subset(final_data, peak_name %in% c("C19/C19+23",  "C20/C20+23", "tricyclics/all")) %>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  geom_line() +
  facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

2 Me Hopanes

subset(final_data, peak_name %in% c("C31_2MHI", "C31_35_2MHI", "C31_2-MHI/C27-C30Steranes"))%>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  geom_line() +
  facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

3 Me Hopane

subset(final_data, peak_name %in% c( "C31_35_3MHI(%)", "C31 3-MHI")) %>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  geom_line() +
  facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

C29ab Ho

subset(final_data, peak_name%in% c("C29ab/allHoab", "C29ab/C29ab+C30ab")) %>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  geom_line() +
  facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

ab/all ho

subset(final_data, peak_name %in% c("C29ab/allHoab","C30ab/allHoab", "C31ab/allHoab", "C32ab/allHoab", "C33ab/allHoab", "C34ab/allHoab", "C35ab/allHoab")) %>%
  ggplot() +
  geom_area(mapping = aes(fill = peak_name)) +
  aes(x = depth, y = ratio, color = peak_name) +
  #facet_wrap(~peak_name, scales = "free") +
  coord_flip() +
  scale_x_reverse() +
  scale_y_continuous() 

subset(final_data, peak_name %in% c("C30ab/allHoab", "C31ab/allHoab", "C32ab/allHoab", "C33ab/allHoab", "C34ab/allHoab", "C35ab/allHoab")) %>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  geom_line() +
  facet_grid(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip() 

Oleanane

subset(final_data, peak_name== "OleananeIndex") %>%
  ggplot() +
  aes(x = depth, y = ratio) +
  geom_point() +
  geom_line() +
 # facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()

Gammacerane, HHI

subset(final_data, peak_name %in% c( "GI", "HHI")) %>%
  ggplot() +
  aes(x = depth, y = ratio, color = peak_name) +
  geom_point() +
  geom_line() +
  facet_wrap(~peak_name, scales = "free") +
  scale_x_reverse() +
  coord_flip()